Perseus: And Live Context Engine MCP Server

Live context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.

Remote serverstreamable-httpPython

What is the Perseus: And Live Context Engine MCP server?

Perseus: And Live Context Engine MCP server exists for a simple reason — assistants are far more useful when they can act on Perseus: And Live Context Engine directly instead of describing what you should do. Live context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.

What you get

Zero to rendered context in three lines — no config spelunking:

What the assistant can call

Once Perseus: And Live Context Engine is connected, these are the calls the assistant has available:

  • perseus_agora — List tasks from the project task board (tasks/*.md files). Use to see what is open, in progress, or completed. Filter by status. Read-only; returns
  • perseus_auto_skill — Instruct the agent to load a specific skill before starting work. Use at the top of context documents to enforce critical hygiene skills (e.g
  • perseus_budget — Declare a token budget for the rendered context (renders as empty text). Enforced by perseus prompt-size: an over-budget render warns — or fails with
  • perseus_capture — Write recent session checkpoints to Perseus Vault as durable memories (#713) — the write side of the memory loop, symmetric to @memory recall
  • perseus_context_diff — Render a compact 'Since last session' delta (#714): git branch/commits, Agora task-board changes, new inbox messages, new checkpoints, and new vault
  • perseus_date — Current date/time
  • perseus_drift — Detect drift between predicted and actual tool usage patterns via the Pythia oracle. Use when tool behavior seems off or after config changes. For
  • perseus_env — Embed environment variable
  • perseus_focus — The global-workspace tier: a small, capacity-bounded (default 32), salience-ranked set of items Perseus broadcasts into context — the shared 'what
  • perseus_health — Audit workspace context health: stale skills, duplicate tasks, oversized output. Use before starting work to catch drift. For deep Daedalus
  • perseus_inbox — Read agent-to-agent messages from the workspace inbox. Use to check for coordination messages from other agents. Filter to unread only. Read-only
  • perseus_include — Include and render another Perseus source file, recursively resolving its directives. Use to compose context from multiple files or share common

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration and credentials

You will need one environment variable: PERSEUS_ALLOW_DANGEROUS. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Perseus: And Live Context Engine's toolset — perseus_agora, perseus_auto_skill, perseus_budget and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Perseus-Computing-LLC; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Perseus: And Live Context Engine.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the perseus: and live context engine mcp server does with a few real requests.

Available tools

ToolWhat it does
perseus_agoraList tasks from the project task board (tasks/*.md files). Use to see what is open, in progress, or completed. Filter by status. Read-only; returns task array with id, title, status, scope.
perseus_auto_skillInstruct the agent to load a specific skill before starting work. Use at the top of context documents to enforce critical hygiene skills (e.g., memory-hygiene, agent-safety). Renders as a mandatory instruction block. Rea
perseus_budgetDeclare a token budget for the rendered context (renders as empty text). Enforced by perseus prompt-size: an over-budget render warns — or fails with strict — with a per-directive byte/token breakdown (#606). Declaration
perseus_captureWrite recent session checkpoints to Perseus Vault as durable memories (#713) — the write side of the memory loop, symmetric to @memory recall. Idempotent per checkpoint (re-render upserts, never duplicates). Use at sessi
perseus_context_diffRender a compact 'Since last session' delta (#714): git branch/commits, Agora task-board changes, new inbox messages, new checkpoints, and new vault session memories since the last recorded snapshot. Use at the top of a
perseus_dateCurrent date/time
perseus_driftDetect drift between predicted and actual tool usage patterns via the Pythia oracle. Use when tool behavior seems off or after config changes. For workspace hygiene checks, prefer perseus_health. Read-only; returns a mar
perseus_envEmbed environment variable
perseus_focusThe global-workspace tier: a small, capacity-bounded (default 32), salience-ranked set of items Perseus broadcasts into context — the shared 'what I'm working on now' set for the agent and its subagents. With no args, re
perseus_healthAudit workspace context health: stale skills, duplicate tasks, oversized output. Use before starting work to catch drift. For deep Daedalus heuristics (cache, directive stats), use perseus_get_health. Read-only; returns
perseus_inboxRead agent-to-agent messages from the workspace inbox. Use to check for coordination messages from other agents. Filter to unread only. Read-only; returns message array with read/unread status.
perseus_includeInclude and render another Perseus source file, recursively resolving its directives. Use to compose context from multiple files or share common sections across workspaces. Bound a growing file with last=N (final N lines
perseus_listList directory contents or structured data. Use to discover files before reading with perseus_read. Supports sorting by name, modified time, or size. Read-only; for hierarchical view, prefer perseus_tree.
perseus_masonQuery the Mason code architecture concept map to find which files implement a feature. Use before editing code to understand where changes should go. Read-only; returns concept map and mapped file list.

How to install the Perseus: And Live Context Engine MCP server

**Cursor** (`.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "perseus": {
      "command": "perseus",
      "args": ["mcp", "serve"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
PERSEUS_ALLOW_DANGEROUSConfiguration value read at startup.Optional

Example prompts to try

  • Use Perseus: And Live Context Engine to perseus agora.
  • Use Perseus: And Live Context Engine to perseus auto skill.
  • Use Perseus: And Live Context Engine to perseus budget.

Frequently asked questions

It connects Perseus: And Live Context Engine to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (perseus_agora, perseus_auto_skill, perseus_budget, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Perseus: And Live Context Engine directly.